Skip to content

Instantly share code, notes, and snippets.

@tsh-code
Created March 4, 2024 08:25
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save tsh-code/d716a8dc6728350f1ab023fb17c3730b to your computer and use it in GitHub Desktop.
Save tsh-code/d716a8dc6728350f1ab023fb17c3730b to your computer and use it in GitHub Desktop.
span marker example
from span_marker import SpanMarkerModel
modelPreTrained = SpanMarkerModel.from_pretrained("tomaarsen/span-marker-mbert-base-multinerd")
modelPreTrained.try_cuda()
def extract_people(text:str):
entities = modelPreTrained.predict(text)
full_names = set()
for entity in entities.ents:
if entity['label'] == 'PER':
# Check if the entity has both a first name and a last name
if len(entity.text.split()) >= 2:
full_names.add(entity.text)
return list(full_names)
content = 'text goes here'
entities = extract_people(content)
print(entities)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment